Space banner


This version is currently available to SaaS customers only. It will be available to on-premises customers soon.

Planning and deploying chatbots

Before implementing chatbots in your organization, you must plan and identify the use cases that you want to address by using chatbot. 

Typically, planning and deploying a chatbot includes the following stages: 

Best practices for planning, implementing, and operating chatbots

The following presentation explains the stages and best practices for planning, implementing, and operating BMC Helix Virtual Agent:

Additional information about IBM Watson Assistant capabilities

The following blog links provide more information about IBM Watson Assistant capabilities. BMC does not endorse the information in these external blog links. The information provided in these links should be used for reference purposes only.

Best practices for IBM Watson Assistant capabilities

Reference in IBM Watson Assistant documentation


  • Disambiguation
  • Self-learning from Disambiguation selections
  • Measure customer effort
  • Controlling the conversational flow Open link

  • Enable your skill to improve itself with autolearning Open link

  • Tracking the impact of autolearning Open link
  • General Guidelines For Chatbot Scripts Open link

  • Enable Your Chatbot To Disambiguate Intelligently With Automatic Learning Open link

  • How To Measure Customer Effort With IBM Watson Assistant Open link

Understanding dialog skill digressions Open link

Why Your Chatbot Conversation Must Allow For Digression Open link

Spelling correction (language dependent) and
Fuzzy marching

Correcting user input Open link

How IBM Watson Assistant Is Correcting User Input For Chatbots Open link

Irrelevancy detection

Defining what's irrelevant Open link

Two Significant Enhancements Were Made To IBM Watson Assistant Open link

Intent conflict resolution

Creating intents Open link

How To Resolve Intent Conflicts With IBM Watson Assistant Open link

Annotated Contextual Entities

Annotation-based method Open link

Contextual Entities with IBM Watson Assistant Open link

Handling compound intents

Tips for capturing information from user input Open link

Dealing With Compound User Intents In IBM Watson Assistant Open link

NLG (Random responses per node)

Adding variety Open link

Chatbots: Creating Natural Language From Structured Data Open link

  • Intent recommendations
  • Example utterances recommendation
  • Getting help with intents Open link

  • Getting intent user example recommendations Open link
  • Taking A Look at IBM Watson Assistant Intent Recommendations Open link
Was this page helpful? Yes No Submitting... Thank you